LeveragingNon-uniformityinFirst-orderNon-convexOptimizationJinchengMei12YueGao1BoDai2CsabaSzepesva´ri31DaleSchuurmans21Abstractinreinforcementlearning(RL)(Agarwaletal.,2020),super-Classicalglobalc...
LearningfromHistoryforByzantineRobustOptimizationSaiPraneethKarimireddy1LieHe1MartinJaggi1Abstracttryingtoderailtheprocess,ormightsimplybemalfunc-tioningandhencesendingarbitrarymessages.EnsuringByz...
Learn2Hop:LearnedOptimizationonRoughLandscapesWithApplicationstoAtomicStructuralOptimizationAmilMerchant12LukeMetz1SamSchoenholz1EkinDogusCubuk1AbstractFigure1.Schematicdiagramofthedifficultiesofgl...
Learner-PrivateConvexOptimizationJiamingXu1KuangXu2DanaYang1Abstract1.IntroductionConvexOptimizationwithfeedbackisaframe-ConvexOptimizationwithfeedbackisaparadigminwhichworkwherealearnerreliesonite...
ModelDistillationforRevenueOptimization:InterpretablePersonalizedPricingMaxBiggs1WeiSun2MarkusEttl2Abstractmainconcernsisthatthemostaccuratepredictionmodelsareoftennon-parametricfunctionswhichareco...
IntermediateLayerOptimizationforInverseProblemsusingDeepGenerativeModelsGiannisDaras1JosephDean1AjilJalal1AlexandrosG.Dimakis1Abstractthatrelyonapre-trainedgenerator,buildingonthegeneralframeworkin...
Infinite-DimensionalOptimizationforZero-SumGamesviaVariationalTransportLewisLiu1YufengZhang2ZhuoranYang3RezaBabanezhad4ZhaoranWang2Abstract(NNs)),whichisofindependentinterest.GameOptimizationhasbee...
ImplicitRate-ConstrainedOptimizationofNon-decomposableObjectivesAbhishekKumar1HarikrishnaNarasimhan1AndrewCotter1Abstractetal.,2017;Cotteretal.,2019a).Moreover,manyofthemetricsthatweareinterestedin...
GuidedExplorationwithProximalPolicyOptimizationusingaSingleDemonstrationGabrieleLibardi1SebastianDittert1GianniDeFabritiis12AbstractLearningfromdemonstrationsallowstodirectlybypassthisproblembutito...
FederatedCompositeOptimizationHonglinYuan12ManzilZaheer3SashankReddi3AbstractFigure1.Resultsonsparse(`1-regularized)logisticregres-sionforafederatedfMRIdatasetbasedon(Haxby,2001).FederatedLearning(...
ExactOptimizationofConformalPredictorsviaIncrementalandDecrementalLearningGiovanniCherubin1KonstantinosChatzikokolakis2MartinJaggi3Abstractclustering(Cherubinetal.,2015).Furthermore,theycanbeusedto...
DebiasingaFirst-orderHeuristicforApproximateBi-levelOptimizationValeriiLikhosherstov1XingyouSong2KrzysztofChoromanski23JaredDavis45AdrianWeller16AbstractZu¨gner&Gu¨nnemann,2019)andmodel-agnosticm...
DuelingConvexOptimizationAadirupaSaha1TomerKoren2YishayMansour2Abstractactivelyqueriedpoints(Flaxmanetal.,2005;Ghadimi&Lan,2013;Bubecketal.,2017).DuetoitsgreatpracticalWeaddresstheproblemofconvexop...
DORO:DistributionalandOutlierRobustOptimizationRuntianZhai1ChenDan1J.ZicoKolter1PradeepRavikumar1Abstractshiftproblems,suchaslearningforalgorithmicfairness(Dworketal.,2012;Barocas&Selbst,2016)where...
DistributionallyRobustOptimizationwithMarkovianDataMengmengLi1TobiasSutter1DanielKuhn1Abstractrespondingtothetrainingsamplesandsolvestheresultingempiricalriskminimizationproblem(Shapiroetal.,2014)....
Communication-EfficientDistributedOptimizationwithQuantizedPreconditionersFoivosAlimisis1PeterDavies2DanAlistarh23AbstractInthispaper,wefocusonthecommunication(bit)com-plexityoftheclassicempiricalr...
CollaborativeBayesianOptimizationwithFairRegretRachaelHweeLingSim1YehongZhang2BryanKianHsiangLow1PatrickJaillet3Abstractperformancebysequentiallyselectinginputqueriesforeval-uatingtheobjectivefunct...
ConvexVST:AConvexOptimizationApproachtoVariance-stabilizingTransformationMengfanWang1BoyuLyu1GuoqiangYu1AbstractVSTproblemhasbeenthesubjectofextensivetheoreticalandexperimentalstudiesbecauseofitsbr...
BayesianOptimizationoverHybridSpacesAryanDeshwal1SyrineBelakaria1JanardhanRaoDoppa1AbstractBelakariaetal.,2019;Zhouetal.,2020;Belakariaetal.,2020e;c;a;f).ThekeyideabehindBOistolearnasurrogateWecons...
BORE:BayesianOptimizationbyDensity-RatioEstimationLouisC.Tiao12AaronKlein3MatthiasSeeger3EdwinV.Bonilla21Ce´dricArchambeau3FabioRamos14Abstractdensity1(x)BayesianOptimization(BO)isamongthemostg(x)...
